CN109241516A - A kind of intelligent Auto-generating Test Paper method based on improved adaptive GA-IAGA - Google Patents
A kind of intelligent Auto-generating Test Paper method based on improved adaptive GA-IAGA Download PDFInfo
- Publication number
- CN109241516A CN109241516A CN201811279883.9A CN201811279883A CN109241516A CN 109241516 A CN109241516 A CN 109241516A CN 201811279883 A CN201811279883 A CN 201811279883A CN 109241516 A CN109241516 A CN 109241516A
- Authority
- CN
- China
- Prior art keywords
- individual
- population
- topic
- fitness
- paper
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000012360 testing method Methods 0.000 title claims abstract description 32
- 238000000034 method Methods 0.000 title claims abstract description 31
- 230000003044 adaptive effect Effects 0.000 title claims abstract description 14
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 21
- 230000002068 genetic effect Effects 0.000 claims abstract description 17
- 238000012986 modification Methods 0.000 claims abstract description 11
- 230000004048 modification Effects 0.000 claims abstract description 11
- 238000005086 pumping Methods 0.000 claims abstract description 6
- 238000001514 detection method Methods 0.000 claims abstract description 4
- 241000009298 Trigla lyra Species 0.000 claims abstract description 3
- 238000004321 preservation Methods 0.000 claims abstract description 3
- 238000012546 transfer Methods 0.000 claims abstract description 3
- 238000004364 calculation method Methods 0.000 claims description 6
- 230000035772 mutation Effects 0.000 claims description 5
- 238000011156 evaluation Methods 0.000 claims description 3
- 238000000605 extraction Methods 0.000 claims description 3
- 238000011835 investigation Methods 0.000 claims description 2
- 239000000284 extract Substances 0.000 description 4
- 238000007726 management method Methods 0.000 description 4
- 230000008859 change Effects 0.000 description 2
- 230000011218 segmentation Effects 0.000 description 2
- 229910017435 S2 In Inorganic materials 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 210000000349 chromosome Anatomy 0.000 description 1
- 238000007796 conventional method Methods 0.000 description 1
- 230000001186 cumulative effect Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000010353 genetic engineering Methods 0.000 description 1
- 230000008676 import Effects 0.000 description 1
- 230000000977 initiatory effect Effects 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 238000012913 prioritisation Methods 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 108090000623 proteins and genes Proteins 0.000 description 1
- 230000004044 response Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/10—Text processing
- G06F40/166—Editing, e.g. inserting or deleting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/12—Computing arrangements based on biological models using genetic models
- G06N3/126—Evolutionary algorithms, e.g. genetic algorithms or genetic programming
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Theoretical Computer Science (AREA)
- Biophysics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Computational Linguistics (AREA)
- General Physics & Mathematics (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Evolutionary Biology (AREA)
- Artificial Intelligence (AREA)
- General Engineering & Computer Science (AREA)
- Bioinformatics & Computational Biology (AREA)
- General Health & Medical Sciences (AREA)
- Evolutionary Computation (AREA)
- Data Mining & Analysis (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Biomedical Technology (AREA)
- Genetics & Genomics (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Physiology (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Investigating Or Analysing Biological Materials (AREA)
Abstract
The present invention provides a kind of intelligent Auto-generating Test Paper method based on improved adaptive GA-IAGA, and A. creates an exam pool or opens an exam pool；B. chapters and sections management, examination point management, the management of topic type, the setting of group volume, Examination Paper Template management and test paper classifying are carried out to exam pool；C. single questions record of examination question enters, repeats detection, transfer, batch is deleted and modification；D. pumping topic is carried out by genetic algorithm, group is rolled up, then preservation or export；E. typing record and Pipers database are checked；F. the recycle bin and collection and fast browsing of test item bank are checked.It has fully considered the various problems in practical application, there is very strong practicability.Many constraint condition is just met in initialization population, accelerates the convergence of algorithm, avoids the unnecessary time, and system group volume is more efficient.
Description
Technical field
The present invention relates to automatic volume group technical field, in particular to a kind of intelligent Auto-generating Test Paper side based on improved adaptive GA-IAGA
Method.
Background technique
It is universal with computer, people can use computer solve the problems, such as it is very much.For teacher, one non-
Often important work is exactly to test to the successes achieved in teaching, and the main method of inspection is exactly to pass through examination, and a set of difficulty is moderate,
The reasonable paper of Distribution of knowledge gists seems most important for examination.Traditional manual group volume method is than cumbersome, Er Qiezhi
Amount hardly results in guarantee.The tactic of generating test paper that existing papers generation system uses has random choice method, backtracking heuristic, error compensation
Method, prioritization schemes method and genetic algorithm, wherein more scientific and effective tactic of generating test paper is genetic algorithm.
Currently, having the method for carrying out automatic volume group using genetic algorithm, the China of 102184345 A of Publication No. CN
Patent discloses a kind of " the group volume method based on genetic algorithm ", and the Chinese patent of 104504627 A of Publication No. CN discloses
" a kind of automatic volume group method using genetic algorithm ", but these methods can have convergence too early in practical applications, occur
The problem of locally optimal solution, or the problem of leading to cannot get optimal solution and wasting time can not be restrained.Therefore, heredity is utilized
During algorithm carries out automatic volume group, the step of algorithm, is improved according to actual scene, to meet actual needs.
Summary of the invention
In order to solve the problems, such as described in background technique, the present invention provides a kind of intelligent Auto-generating Test Paper side based on improved adaptive GA-IAGA
Method, the population that a new generation is selected by way of roulette can avoid the occurrence of locally optimal solution, and in initialization population
When just meet the constraint of topic type, total score, knowledge point and topic quantity, a group volume can be exited if being unable to satisfy, avoids nothing
The iteration of effect, to save a large amount of time.
In order to achieve the above object, the present invention is implemented with the following technical solutions:
A kind of intelligent Auto-generating Test Paper method based on improved adaptive GA-IAGA, includes the following steps:
A. it creates an exam pool or opens an exam pool；
B. chapters and sections management, examination point management, the management of topic type, the setting of group volume, Examination Paper Template management and paper point are carried out to exam pool
Class；
C. single questions record of examination question enters, repeats detection, transfer, batch is deleted and modification；
D. pumping topic is carried out by genetic algorithm, group is rolled up, then preservation or export；
E. typing record and Pipers database are checked；
F. the recycle bin and collection and fast browsing of test item bank are checked.
A newly-built exam pool in the step A includes two states:
(1) exam pool that current system is not turned on then creates an exam pool completely；
(2) there is the exam pool opened in current system, can choose when newly-built and retains exam pool structure.
Pumping topic is carried out by genetic algorithm in the step D, group volume comprises the steps of:
(1) the relevant parameter of genetic algorithm, inclusive fitness desired value, maximum number of iterations are set in system setting
With initial population size；
(2) select or newly-built group volume setting, group volume setting include a group volume setting title, topic title, small topic number and
Topic type；
(3) suitable extraction condition is set, including paper total score, degree-of-difficulty factor and the knowledge point of investigation；
(4) initial according to the Population Size set under the constraint of satisfaction topic type, every kind of topic type number and paper total score
Change population；
(5) fitness of each individual in population is calculated；
(6) fitness for judging whether there is individual meets desired value and whether the number of iterations reaches maximum value；If there is
Individual meets desired value, and corresponding topic is just extracted and terminated iteration, terminates if the number of iterations reaches maximum value
Iteration, display do not obtain as a result, otherwise, carrying out in next step；
(7) selection and crossover operation are carried out to the individual in population, and calculates the fitness of each individual in new population；
(8) fitness for judging whether there is individual meets desired value and whether the number of iterations reaches maximum value；If there is
Individual meets desired value, and corresponding topic is just extracted and terminated iteration, terminates if the number of iterations reaches maximum value
Iteration, display do not obtain as a result, otherwise, carrying out in next step；
(9) mutation operation is carried out to the individual in population, generates the population of a new generation, and return to step (5).
Wherein: it is described according to the Population Size initialization population set the step of it is as follows:
(1) according to the difference of topic type, the examination question that all satisfaction topic types and knowledge point require is extracted from exam pool, then again with
The topic that machine extracts specified quantity is added in individual, generates a new individual；
(2) judge whether new individual meets the total score constraint of desired paper, if it is satisfied, then new individual is added to population
In the middle, otherwise new individual is invalid, regenerates；
(3) when the individual amount in population reaches the population scale of setting, initialization population is completed, then in population
Individual successively calculate fitness and knowledge dot coverage, the judgment basis as next step.
The calculation method for calculating the fitness of each individual in population are as follows:
F=1- (1-M/N) * k1- | P-p | * k2
Wherein, M indicates that the knowledge point number after union is sought in the knowledge point that each topic includes in an individual, and N is expectation
The knowledge point number for including in paper, P are the degree-of-difficulty factor of desired paper, and p is degree-of-difficulty factor of the individual after calculating；
K1 is proportionality coefficient of the knowledge point in evaluation fitness, and k2 is the ratio of degree-of-difficulty factor；Indicate that fitness is only examined as k1=0
Consider question difficulty coefficient, indicates that fitness only considers knowledge point as k2=0；The calculation method of p is each topic in individual
Score multiplies degree-of-difficulty factor and sums, then again divided by the gross score of paper.
The method that the individual in population carries out selection use is roulette wheel selection；Its step are as follows:
(1) fitness of all individuals and the gross area as wheel disc in population are calculated；
(2) number of a 0-1 is randomly generated, then multiplied by fitness and, as selected reference point；
(3) since an individual, it is superimposed fitness, when the fitness of superposition is more than or equal to reference point, is
It avoids repeating to choose the same individual, to judge whether current individual was selected, if current individual was not selected,
Current individual is selected；
(4) step (2) and (3) are repeated, the individual until generating specified quantity, then selection operation is completed.
Compared with prior art, the beneficial effects of the present invention are:
1, the various problems in practical application have been fully considered, there is very strong practicability.
2, many constraint condition is just met in initialization population, accelerates the convergence of algorithm, and it is unnecessary to avoid
Time, system group volume it is more efficient.
3, in the step of the method for the present invention: (1), the constraint of satisfaction topic type, topic quantity and total score under initialization population, and
Judge whether current exam pool meets basic group rollback request；(2), individual is calculated by knowledge dot coverage and degree-of-difficulty factor
Fitness simultaneously judges whether to meet the requirements, and meets end group volume, otherwise executes (3)；(3), genetic manipulation is carried out to current population,
Wherein crossover operation realizes multiple point crossover by segmentation single point crossing；(4), it recalculates fitness and judges whether to meet and want
It asks, satisfaction terminates, and otherwise executes (5)；The population of a new generation is selected using the mode of roulette；It is more to be segmented single point crossing realization
Point intersects；(5), it does not destroy in the case that individual has met constraint and makes a variation, step (2)-(5) are repeated, until algorithmic statement.
Detailed description of the invention
Fig. 1 is the flow chart of the intelligent Auto-generating Test Paper method provided by the invention based on improved adaptive GA-IAGA；
Fig. 2 is the instance graph of a chromosome in genetic algorithm.
Specific embodiment
Specific embodiment provided by the invention is described in detail below in conjunction with attached drawing.
A kind of intelligent Auto-generating Test Paper method based on improved adaptive GA-IAGA, comprising the following steps:
S1. the binary file that a suffix is STK is created or open after logging into this system, for saving examination question
The overall structure information in library, including chapters and sections catalogue, topic type, knowledge point etc..
S2. create or safeguard test item bank structural information, typing and modification including chapters and sections catalogue, the typing of topic type and
Modification, the typing and modification of knowledge point, the addition and modification of Examination Paper Template, the newly-built and modification of test paper classifying, group volume setting
Newly-built and modification, can also import and export chapters and sections catalogue by Excel table.
S3. the initiation parameter of genetic algorithm is configured in system setting, inclusive fitness desired value, maximum change
Generation number and initial population size.
S4. the group set in S2 a volume setting is selected, the overall structure of paper is then initialized, it can also be to S2
In group volume setting modify after reinitialize or create the volume setting of group.
S5. the constraint condition of paper is configured, the degree-of-difficulty factor and paper of total score, paper including paper will be investigated
Knowledge point.
S6. suitable topic is extracted from test item bank using the operation of genetic algorithm be combined into a set of constraint condition that meets
Paper.
S7. it saves in the clamp for test papers that paper is set to S2 or exports to local hard drive according to the template that S2 is set
On.
Further, there are two types of modes for the binary file that a newly-built suffix is STK, and it is former both to can choose reservation
The structure of test item bank can also create the test item bank of a blank.
Further, described to open mode there are two types of the binary files that a suffix is STK, it can both pass through file pair
It talks about frame to open, also can be used and open menu opening recently.
Further, the newly-built and modification of the test paper classifying includes two aspects, first is that paper case, second is that clamp for test papers,
It include clamp for test papers in paper case.
Further, the attribute that the newly-built and modification of described group of volume setting includes has a group volume setting title, topic title, small
Inscribe number and topic type.
Further, the operation using genetic algorithm includes selection, intersects and make a variation, the specific steps of which are as follows:
S61. initialization population, Population Size is arranged by system to be determined, first meets desired paper from the total middle selection of test item bank
All topics that topic type and knowledge point require, if selected topic number is less than the number for the topic type that desired paper requires,
Determine that exam pool is unable to satisfy requirement, exits a group volume, appropriate number of topic is otherwise randomly selected from all selected topics, take out
It prevents from repeating to extract topic when taking topic.After all topic types all find enough suitable topics, the total score of these topics is calculated
Whether the total score of satisfaction expectation paper constrains, and is unsatisfactory for, extracts topic again, can't if having extracted 200 times or more again
Meet total score constraint, then determines it is expected that the setting of paper total score is unreasonable, exit a group volume.After meeting total score constraint, so that it may press
Initialization population is carried out according to Population Size, the coding of each individual is exactly the integer number of selected topic in population, according to topic type
Different segment encodings.
S62. fitness is calculated, fitness is determined by two variables of knowledge dot coverage and degree-of-difficulty factor, calculation formula
Are as follows:
F=1- (1-M/N) * k1- | P-p | * k2
Wherein, M indicates that the knowledge point number after union is sought in the knowledge point that each topic includes in an individual, and N is expectation
The knowledge point number for including in paper, P are the degree-of-difficulty factor of desired paper, and p is degree-of-difficulty factor of the individual after calculating,
Calculation method is the score of each topic in individual multiplied by degree-of-difficulty factor and sums, and then sentences the total score of paper again.K1 is to know
Know proportionality coefficient of the point in evaluation fitness, k2 is the ratio of degree-of-difficulty factor.Indicate that fitness only considers examination question as k1=0
Degree-of-difficulty factor indicates that fitness only considers knowledge point as k2=0.
S63. the fitness for judging whether there is individual meets desired value and whether the number of iterations reaches maximum value, the number of iterations
Maximum value by system setting preset or using system default value.Meet desired value if there is individual, just correspondence
Topic extract and terminate iteration, terminate iteration if the number of iterations reaches maximum value, display does not obtain as a result, no
Then, it carries out in next step.
S64. selection operation selects the population of a new generation by way of roulette.First calculate the suitable of all individuals
Response and, select an individual when, the number of a 0-1 is randomly generated, then multiplied by fitness and generate a random value,
The individual of population is traversed, and cumulative to fitness, when accumulated value is greater than random value, then the individual is selected, also to filter weight
Individual in final election, until generating enough individuals, then selection terminates.
S65. crossover operation, segmentation single point crossing finally realize multiple point crossover.All individual random pairs two-by-two, at every kind
The position that an intersection is randomly generated in topic type carries out the swap operation of gene, in this way may be used in the case where meeting the identical situation of score value
To guarantee the total score of paper not by broken ring.Crossover operation is constantly carried out, it, will also be to newly generated until generating enough individuals
Body carries out repeating detection, avoids generating duplicate individual.
S66. a variable position is randomly generated in mutation operation, and selection includes the same of this topic effective knowledge point from exam pool
Type randomly selects the examination question for replacing script with score difference question number examination question in satisfactory examination question, completes to become
ETTHER-OR operation.
S67. the fitness for judging whether there is individual meets desired value and whether the number of iterations reaches maximum value, the number of iterations
Maximum value by system setting preset or using system default value.Meet desired value if there is individual, just correspondence
Topic extract and terminate iteration, terminate iteration if the number of iterations reaches maximum value, display does not obtain as a result, no
Then, step S62 is returned to.
Further, the operation using genetic algorithm includes selection, intersects and variation, when extraction topic prevent
The method for repeating to extract topic use is:
S611. it since qualified examination question set into the range of ending, randomly chooses an examination question and enters individual
Examination question set.
S612. selected examination question is put into the last one position of qualified examination question set by exchange.
S613. the range of selection is subtracted one, makes selection next time that can not choose the examination question being selected, returns to step S611,
Select next examination question.
Fig. 1 is the specific embodiment of the present invention, comprising the following steps:
(1) after setting parameter and constraint condition in systems, click start pumping topic, system first can initialization population,
Each individual is exactly a series of number of topics in population, as shown in Fig. 2, being exactly an individual, indicates to extract a set of shared
23 problem purpose papers include many such individuals in population.
(2) population will calculate the fitness of each individual after generating, with this to determine whether there is suitable paper to produce
It is raw, if fitness does not have up to standard or the number of iterations not reach maximum value, will do it in next step.
(3) selection and crossover operation are carried out to population, fitness then is recalculated to new population, and judge the number of iterations
Whether reach maximum value and meets desired value either with or without the fitness of individual, it, can be to the individual of population if all do not met
Mutation operation is carried out, a group volume is otherwise terminated.
(4) mutation operation is carried out to the individual of original seed group, generates the population of a new generation, and return to step (2).
Above embodiments are implemented under the premise of the technical scheme of the present invention, give detailed embodiment and tool
The operating process of body, but protection scope of the present invention is not limited to the above embodiments.Method therefor is such as without spy in above-described embodiment
Not mentionleting alone bright is conventional method.
Claims (6)
1. a kind of intelligent Auto-generating Test Paper method based on improved adaptive GA-IAGA, which comprises the steps of:
A. it creates an exam pool or opens an exam pool；
B. chapters and sections management, examination point management, the management of topic type, the setting of group volume, Examination Paper Template management and test paper classifying are carried out to exam pool；
C. single questions record of examination question enters, repeats detection, transfer, batch is deleted and modification；
D. pumping topic is carried out by genetic algorithm, group is rolled up, then preservation or export；
E. typing record and Pipers database are checked；
F. the recycle bin and collection and fast browsing of test item bank are checked.
2. a kind of intelligent Auto-generating Test Paper method based on improved adaptive GA-IAGA according to claim 1, which is characterized in that the step
A newly-built exam pool in rapid A includes two states:
(1) exam pool that current system is not turned on then creates an exam pool completely；
(2) there is the exam pool opened in current system, can choose when newly-built and retains exam pool structure.
3. a kind of intelligent Auto-generating Test Paper method based on improved adaptive GA-IAGA according to claim 1, which is characterized in that the step
Pumping topic is carried out by genetic algorithm in rapid D, group volume comprises the steps of:
(1) the relevant parameter of genetic algorithm is set in system setting, inclusive fitness desired value, maximum number of iterations and just
Beginning Population Size；
(2) it selects or newly-built group volume setting, group volume setting includes group volume setting title, topic title, small topic number and topic type；
(3) suitable extraction condition is set, including paper total score, degree-of-difficulty factor and the knowledge point of investigation；
(4) under the constraint of satisfaction topic type, every kind of topic type number and paper total score, according to the Population Size initialization kind set
Group；
(5) fitness of each individual in population is calculated；
(6) fitness for judging whether there is individual meets desired value and whether the number of iterations reaches maximum value；If there is individual
Meet desired value, corresponding topic just extracted and terminated iteration, terminates iteration if the number of iterations reaches maximum value,
Display does not obtain as a result, otherwise, carrying out in next step；
(7) selection and crossover operation are carried out to the individual in population, and calculates the fitness of each individual in new population；
(8) fitness for judging whether there is individual meets desired value and whether the number of iterations reaches maximum value；If there is individual
Meet desired value, corresponding topic just extracted and terminated iteration, terminates iteration if the number of iterations reaches maximum value,
Display does not obtain as a result, otherwise, carrying out in next step；
(9) mutation operation is carried out to the individual in population, generates the population of a new generation, and return to step (5).
4. a kind of intelligent Auto-generating Test Paper method based on improved adaptive GA-IAGA according to claim 3, which is characterized in that described to press
The step of according to the Population Size initialization population set, is as follows:
(1) according to the difference of topic type, the examination question of all satisfaction topic types and knowledge point requirement is extracted from exam pool, it is then random again to take out
It takes the topic of specified quantity to be added in individual, generates a new individual；
(2) judge whether new individual meets the total score constraint of desired paper, work as if it is satisfied, then new individual is added to population
In, otherwise new individual is invalid, regenerates；
(3) when the individual amount in population reaches the population scale of setting, initialization population is completed, then in population
Body successively calculates fitness and knowledge dot coverage, the judgment basis as next step.
5. a kind of intelligent Auto-generating Test Paper method based on improved adaptive GA-IAGA according to claim 3, which is characterized in that the meter
Calculate the calculation method of the fitness of each individual in population are as follows:
F=1- (1-M/N) * k1- | P-p | * k2
Wherein, M indicates that the knowledge point number after union is sought in the knowledge point that each topic includes in an individual, and N is desired paper
In include knowledge point number, P be it is expected paper degree-of-difficulty factor, p be an individual by calculating after degree-of-difficulty factor；K1 is
Proportionality coefficient of the knowledge point in evaluation fitness, k2 are the ratio of degree-of-difficulty factor；Indicate that fitness only considers to try as k1=0
Degree-of-difficulty factor is inscribed, indicates that fitness only considers knowledge point as k2=0；The calculation method of p is the score of each topic in individual
Multiply degree-of-difficulty factor and sum, then again divided by the gross score of paper.
6. a kind of intelligent Auto-generating Test Paper method based on improved adaptive GA-IAGA according to claim 3, which is characterized in that described right
The method that individual in population carries out selection use is roulette wheel selection；Its step are as follows:
(1) fitness of all individuals and the gross area as wheel disc in population are calculated；
(2) number of a 0-1 is randomly generated, then multiplied by fitness and, as selected reference point；
(3) since an individual, it is superimposed fitness, when the fitness of superposition is more than or equal to reference point, to avoid
The same individual is chosen in repetition, to judge whether current individual was selected, if current individual was not selected, currently
Individual is selected；
(4) step (2) and (3) are repeated, the individual until generating specified quantity, then selection operation is completed.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811279883.9A CN109241516A (en) | 2018-10-30 | 2018-10-30 | A kind of intelligent Auto-generating Test Paper method based on improved adaptive GA-IAGA |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811279883.9A CN109241516A (en) | 2018-10-30 | 2018-10-30 | A kind of intelligent Auto-generating Test Paper method based on improved adaptive GA-IAGA |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109241516A true CN109241516A (en) | 2019-01-18 |
Family
ID=65079384
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811279883.9A Pending CN109241516A (en) | 2018-10-30 | 2018-10-30 | A kind of intelligent Auto-generating Test Paper method based on improved adaptive GA-IAGA |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109241516A (en) |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109118402A (en) * | 2018-08-31 | 2019-01-01 | 中国人民解放军军事科学院评估论证研究中心 | A kind of army's cadre's on-line study examination assessment system and method |
| CN109918406A (en) * | 2019-01-27 | 2019-06-21 | 浙江工业大学 | A kind of matter group volume method and papers generation system such as automatic based on maximum clique algorithm |
| CN111667070A (en) * | 2020-05-06 | 2020-09-15 | 华东师范大学 | Intelligent volume combination method based on genetic algorithm |
| CN112509402A (en) * | 2019-08-26 | 2021-03-16 | 北京广益三文教育科技有限公司 | Establishment, issue and anti-counterfeiting method of competitive question bank based on three-dimensional teaching materials and teaching system thereof |
| CN113626474A (en) * | 2021-10-09 | 2021-11-09 | 北京道达天际科技有限公司 | Database random extraction method, device and equipment |
| CN117131104A (en) * | 2023-08-28 | 2023-11-28 | 河北望岳信息科技有限公司 | Intelligent question-drawing and winding method and device, electronic equipment and storage medium |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1588308A (en) * | 2004-07-02 | 2005-03-02 | 北京邮电大学 | Method for realizing automatically compiling test paper from item pool using improved genetic calculation |
| CN105825270A (en) * | 2016-03-03 | 2016-08-03 | 云南电网有限责任公司教育培训评价中心 | Automatic test paper generation method for test questions in question bank through genetic algorithm |
| CN107918655A (en) * | 2017-11-16 | 2018-04-17 | 重庆三峡学院 | A kind of test paper generation management control system and control method |
-
2018
- 2018-10-30 CN CN201811279883.9A patent/CN109241516A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1588308A (en) * | 2004-07-02 | 2005-03-02 | 北京邮电大学 | Method for realizing automatically compiling test paper from item pool using improved genetic calculation |
| CN105825270A (en) * | 2016-03-03 | 2016-08-03 | 云南电网有限责任公司教育培训评价中心 | Automatic test paper generation method for test questions in question bank through genetic algorithm |
| CN107918655A (en) * | 2017-11-16 | 2018-04-17 | 重庆三峡学院 | A kind of test paper generation management control system and control method |
Non-Patent Citations (3)
| Title |
|---|
| 周艳丽: "基于改进遗传算法的自动组卷问题研究", 《计算机仿真》 * |
| 张烈超等: "基于遗传算法智能组卷的考试***设计及实现", 《武汉交通职业学院学报》 * |
| 朱铁樱: "多课程并行考试及题库管理***的设计与实现", 《电脑知识与技术》 * |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109118402A (en) * | 2018-08-31 | 2019-01-01 | 中国人民解放军军事科学院评估论证研究中心 | A kind of army's cadre's on-line study examination assessment system and method |
| CN109118402B (en) * | 2018-08-31 | 2021-12-07 | 中国人民解放军军事科学院评估论证研究中心 | Army cadre online learning, examination and evaluation system and method |
| CN109918406A (en) * | 2019-01-27 | 2019-06-21 | 浙江工业大学 | A kind of matter group volume method and papers generation system such as automatic based on maximum clique algorithm |
| CN109918406B (en) * | 2019-01-27 | 2021-07-23 | 浙江工业大学 | Maximum clique algorithm-based automatic equal-quality volume combining method and volume combining system |
| CN112509402A (en) * | 2019-08-26 | 2021-03-16 | 北京广益三文教育科技有限公司 | Establishment, issue and anti-counterfeiting method of competitive question bank based on three-dimensional teaching materials and teaching system thereof |
| CN111667070A (en) * | 2020-05-06 | 2020-09-15 | 华东师范大学 | Intelligent volume combination method based on genetic algorithm |
| CN113626474A (en) * | 2021-10-09 | 2021-11-09 | 北京道达天际科技有限公司 | Database random extraction method, device and equipment |
| CN117131104A (en) * | 2023-08-28 | 2023-11-28 | 河北望岳信息科技有限公司 | Intelligent question-drawing and winding method and device, electronic equipment and storage medium |
| CN117131104B (en) * | 2023-08-28 | 2024-02-27 | 河北望岳信息科技有限公司 | Intelligent question-drawing and winding method and device, electronic equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109241516A (en) | A kind of intelligent Auto-generating Test Paper method based on improved adaptive GA-IAGA | |
| Lee et al. | Process-embedded data integrity | |
| Xiong et al. | Optimal experimental design for staggered rollouts | |
| Selten | Aspiration adaptation theory | |
| Sabirianova | The great human capital reallocation: A study of occupational mobility in transitional Russia | |
| Meyer et al. | A multiattribute model of consumer choice during product learning | |
| Cripps et al. | Heuristics and biases in timing the replacement of durable products | |
| Wilson | Compact rulesets from XCSI | |
| CN106777402B (en) | A kind of image retrieval text method based on sparse neural network | |
| Wen et al. | A knowledge-based intelligent decision support system for national defense budget planning | |
| CN108509573A (en) | Book recommendation method based on matrix decomposition collaborative filtering and system | |
| CN108647249A (en) | Public sentiment data prediction technique, device, terminal and storage medium | |
| CN107451230A (en) | A kind of answering method and question answering system | |
| CN106202377A (en) | A kind of online collaborative sort method based on stochastic gradient descent | |
| CN110059190A (en) | A kind of user's real-time point of view detection method based on social media content and structure | |
| CN115131131A (en) | Credit risk assessment method for unbalanced data set multi-stage integration model | |
| Li | Research on evaluation method of physical education teaching quality in colleges and universities based on decision tree algorithm | |
| Müller et al. | Scientific machine and deep learning investigations of the local buckling behaviour of hollow sections | |
| Bintley | Times series analysis with REVEAL | |
| CN107704944B (en) | Construction method of stock market fluctuation interval prediction model based on information theory learning | |
| CN111028086A (en) | Enhanced index tracking method based on clustering and LSTM network | |
| CN110084376A (en) | To the method and device of the automatic branch mailbox of data | |
| Bozdogan et al. | Information complexity criteria for detecting influential observations in dynamic multivariate linear models using the genetic algorithm | |
| CN115034847A (en) | Product recommendation method, system, storage medium and equipment based on deep learning | |
| Zhao | Research on Construction of Educational Management Model Based on Data Mining Technology |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190118 |
|
| RJ01 | Rejection of invention patent application after publication |